• The Journal of Information Technology
• /
• v.9 no.4
• /
• pp.65-74
• /
• 2006

The back propagation of neural networks has the problems of falling into local minimum and delay of the speed by the iterative learning. An algorithm to solve the problem and improve the speed of the learning was already proposed in[8], which updates the learning parameter related with the connection weight. In this paper, we propose the algorithm generating initial weight to improve the efficiency of the algorithm by offering the difference between the input vector and the target signal to the generating function of initial weight. The algorithm proposed here can classify more than 98.75% of the handwritten digits and this rate shows 30% more effective than the other previous methods.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.4
• /
• pp.2148-2161
• /
• 2019

In this paper, we present a real-time cattle action recognition algorithm to detect the estrus phase of cattle from a live video stream. In order to classify cattle movement, specifically, to detect the mounting action, the most observable sign of the estrus phase, a simple yet effective feature description exploiting motion history images (MHI) is designed. By learning the proposed features using the support vector machine framework, various representative cattle actions, such as mounting, walking, tail wagging, and foot stamping, can be recognized robustly in complex scenes. Thanks to low complexity of the proposed action recognition algorithm, multiple cattle in three enclosures can be monitored simultaneously using a single fisheye camera. Through extensive experiments with real video streams, we confirmed that the proposed algorithm outperforms a conventional human action recognition algorithm by 18% in terms of recognition accuracy even with much smaller dimensional feature description.

• The Journal of Korea Robotics Society
• /
• v.14 no.3
• /
• pp.211-220
• /
• 2019

Surface electromyogram (sEMG), which is a bio-electrical signal originated from action potentials of nerves and muscle fibers activated by motor neurons, has been widely used for recognizing motion intention of robotic prosthesis for amputees because it enables a device to be operated intuitively by users without any artificial and additional work. In this paper, we propose a training-free unsupervised sEMG pattern recognition algorithm. It is useful for the gesture recognition for the amputees from whom we cannot achieve motion labels for the previous supervised pattern recognition algorithms. Using the proposed algorithm, we can classify the sEMG signals for gesture recognition and the calculated threshold probability value can be used as a sensitivity parameter for pattern registration. The proposed algorithm was verified by a case study of a patient with partial-hand amputation.

• Journal of Digital Contents Society
• /
• v.14 no.4
• /
• pp.463-469
• /
• 2013

The set-based POI search algorithm showed better performance than the existing hard matching search when inaccurate queries are entered. In the set-based POI search algorithm, however, there is a problem that can't classify duplicate characters within a record. This is due to it's 'set-based' search property. To solve this problem, we improve the existing set-based POI search algorithm. In this paper, we propose and implement an improved set-based POI search algorithm that is able to deal duplicate characters properly. From the experimental results, we can find that our technique for duplicate characters improves the performance of the existing set based POI search algorithm.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.3
• /
• pp.976-990
• /
• 2020

The k-means algorithm is widely used in academia and industry due to easy and simple implementation, enabling fast learning for complex datasets. However, k-means struggles to classify datasets without prior knowledge of specific domains. We proposed the repulsive k-means (RK-means) algorithm in a previous study to improve the k-means algorithm, using the repulsive force concept, which allows deleting unnecessary cluster centroids. Accordingly, the RK-means enables to classifying of a dataset without domain knowledge. However, three main problems remain. The RK-means algorithm includes a cluster repulsive force offset, for clusters confined in other clusters, which can cause cluster locking; we were unable to prove RK-means provided optimal convergence in the previous study; and RK-means shown better performance only normalize term and weight. Therefore, this paper proposes the advanced RK-means (ARK-means) algorithm to resolve the RK-means problems. We establish an initialization strategy for deploying cluster centroids and define a metric for the ARK-means algorithm. Finally, we redefine the mass and normalize terms to close to the general dataset. We show ARK-means feasibility experimentally using blob and iris datasets. Experiment results verify the proposed ARK-means algorithm provides better performance than k-means, k'-means, and RK-means.

• Management Science and Financial Engineering
• /
• v.15 no.1
• /
• pp.81-96
• /
• 2009

Data mining, specially clustering is one of exciting research areas for ant based algorithms. Ant clustering algorithm, however, has many difficulties for resolving practical situations in clustering. We propose a new grid-based ant colony algorithm for clustering of data. The previous ant based clustering algorithms usually tried to find the clusters during picking up or dropping down process of the items of ants using some stigmergy information. In our ant clustering algorithm we try to make the ants reflect neighborhood information within the storage nests. We use two ant classes, search ants and labor ants. In the initial step of the proposed algorithm, the search ants try to guide the characteristics of the storage nests. Then the labor ants try to classify the items using the guide in-formation that has set by the search ants and the stigmergy information that has set by other labor ants. In this procedure the clustering decision of ants is quickly guided and keeping out of from the stagnated process. We experimented and compared our algorithm with other known algorithms for the known and statistically-made data. From these experiments we prove that the suggested ant mining algorithm found the clusters quickly and effectively comparing with a known ant clustering algorithm.

• Proceedings of the IEEK Conference
• /
• 2000.06d
• /
• pp.222-225
• /
• 2000

Human frequently communicate non-linguistic information with gesture. So, we must develop efficient and fast gesture recognition algorithms for more natural human-computer interaction. However, it is difficult to recognize gesture automatically because human's body is three dimensional object with very complex structure. In this paper, we suggest a method which is able to detect key frames and frame changes, and to classify image sequence into some gesture groups. Gesture is classifiable according to moving part of body. First, we detect some frames that motion areas are changed abruptly and save those frames as key frames, and then use the frames to classify sequences. We symbolize each image of classified sequence using Principal Component Analysis(PCA) and clustering algorithm since it is better to use fewer components for representation of gestures. Symbols are used as the input symbols for the Hidden Markov Model(HMM) and recognized as a gesture with probability calculation.

• Proceedings of the CALSEC Conference
• /
• 2005.03a
• /
• pp.189-194
• /
• 2005

Many studies have been conducted to classify documents, and to extract useful information from documents. However, most search engines have used a keyword based method. This method does not search and classify documents effectively. This paper identifies structures of XML document based on the fact that the XML document has a structural document using a set theory, which is suggested by Broder, and attempts a test for clustering XML document by applying a k-nearest neighbor algorithm. In addition, this study investigates the effectiveness of the clustering technique for large scaled data, compared to the existing bitmap method, by applying a test, which reveals a difference between the clause based documents instead of using a type of vector, in order to measure the similarity between the existing methods.

• Journal of Electrical Engineering and Technology
• /
• v.5 no.4
• /
• pp.666-671
• /
• 2010

Multi-layer perceptron neural networks have been constructed to classify four types of defects in steam generator tubes. Three features are extracted from the signals of the eddy current testing method. These include maximum impedance, phase angle at the point of maximum impedance, and an angle between the point of maximum impedance and the point of half the maximum impedance. Two hundred sets of these features are used for training and assessing the networks. Two approaches are involved to train the networks and to classify the defect type. One is the conjugate gradient method and the other is the Broydon-Fletcher-Goldfarb-Shanno method which is recognized as the most popular algorithm of quasi-Newton methods. It is found from the computation results that the training time of the Broydon-Fletcher-Goldfarb-Shanno method is much faster than that of the conjugate gradient method in most cases. On the other hand, no significant difference of the classification performance between the two methods is observed.

• Journal of Institute of Control, Robotics and Systems
• /
• v.15 no.9
• /
• pp.899-905
• /
• 2009

There are many different types of surface defects on semiconductor Integrated Chips (IC's) caused by various factors during manufacturing process, such as Scratch, Flash, Resin bleed, and Melting. These defects must be detected and classified by an inspection system for productivity improvement and effective process control. Among defects, in particular, Resin bleed and Melting are the most difficult ones to classify accurately. The brightness value and the shape of Resin bleed and Melting defects are so similar that normally it is difficult to classify the Resin bleed and Melting. In this paper, we propose a segmenting method and a set of features for detecting and classifying the Resin bleed and Melting defects.